Research map / Architectures and efficiency / Attention and transformers
DCMM-Transformer: Degree-Corrected Mixed-Membership Attention for Medical Imaging
Huimin Cheng, Xiaowei Yu, Shushan Wu, Luyang Fang, Chao Cao, Jing Zhang, Tianming Liu, Dajiang Zhu, Wenxuan Zhong, Ping Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add entropy regularization on soft memberships (ablation) | DCMM-Transformer · Average over 5 medical datasets | accuracy (%): 84.4 -> 87.3 | Improved |
| add degree correction (node degree parameters) (ablation) | DCMM-Transformer · Average over 5 medical datasets | accuracy (%): 85.0 -> 87.3 | Improved |
| add mixed-membership (soft memberships) (ablation) | DCMM-Transformer · Average over 5 medical datasets | accuracy (%): 84.7 -> 87.3 | Improved |
| add entropy regularization (ablation) | DCMM-Transformer · ADNI | accuracy (%): 66.7 -> 74.1 | Improved |
| add degree correction (ablation) | DCMM-Transformer · ChestXray | accuracy (%): 94.9 -> 96.0 | Improved |
| add DCMM additive bias to ViT-S attention (vs plain ViT) | DCMM-Transformer · Average over 5 medical datasets | accuracy (%): 83.6 -> 87.3 | Improved |
| replace SBM-Transformer binary masking with DCMM additive bias | DCMM-Transformer · Average over 5 medical datasets | accuracy (%): 83.1 -> 87.3 | Improved |
| DCMM bias vs MaxViT (best baseline) | DCMM-Transformer · EyeDisease | accuracy (%): 93.2 -> 93.3 | No clear effect |
| vary number of communities L from 80 to 180 (ablation) | DCMM-Transformer · INbreast, EyeDisease, ChestXray | accuracy | No clear effect |
Closest papers by meaning
- EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation (CVPR 2024 · similarity 0.86)
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · similarity 0.85)
- Multi-modal Vision Pre-training for Medical Image Analysis (CVPR 2025 · similarity 0.85)
- DTMFormer: Dynamic Token Merging for Boosting Transformer-Based Medical Image Segmentation (AAAI 2024 · similarity 0.85)
- Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification (AAAI 2025 · similarity 0.85)
- Statistical Test for Attention Maps in Vision Transformers (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
